ColorNet: Investigating the importance of color spaces for image classification⋆ Shreyank N Gowda1 and Chun Yuan2 1 Computer Science Department, Tsinghua University, Beijing 10084, China
[email protected] 2 Graduate School at Shenzhen, Tsinghua University, Shenzhen 518055, China
[email protected] Abstract. Image classification is a fundamental application in computer vision. Recently, deeper networks and highly connected networks have shown state of the art performance for image classification tasks. Most datasets these days consist of a finite number of color images. These color images are taken as input in the form of RGB images and clas- sification is done without modifying them. We explore the importance of color spaces and show that color spaces (essentially transformations of original RGB images) can significantly affect classification accuracy. Further, we show that certain classes of images are better represented in particular color spaces and for a dataset with a highly varying number of classes such as CIFAR and Imagenet, using a model that considers multi- ple color spaces within the same model gives excellent levels of accuracy. Also, we show that such a model, where the input is preprocessed into multiple color spaces simultaneously, needs far fewer parameters to ob- tain high accuracy for classification. For example, our model with 1.75M parameters significantly outperforms DenseNet 100-12 that has 12M pa- rameters and gives results comparable to Densenet-BC-190-40 that has 25.6M parameters for classification of four competitive image classifica- tion datasets namely: CIFAR-10, CIFAR-100, SVHN and Imagenet. Our model essentially takes an RGB image as input, simultaneously converts the image into 7 different color spaces and uses these as inputs to individ- ual densenets.